arXiv subjects

Wenhan Lyu

Publications and source records attributed to Wenhan Lyu.

12 recordsLinked to original sources

arXiv2026

ArchSim: Computer Architecture Simulation as a Service

Conducting a complete computer architecture simulation study is challenging because configuration, execution, and analysis are often encoded implicitly in scripts or directory conventions rather than represented explicitly. As a result, studies are difficult to scale, hard to reproduce, and dependent on custom tooling at every stage. We present ArchSim, which makes the structure of a simulation study explicit. In ArchSim, hardware topologies are described as declarative graphs that automatically generate executable simulation code, eliminating hand-written simulator programs. Stateless runners autonomously claim and execute jobs from a shared experiment store, enabling configuration-benchmark matrices to scale without manual orchestration. Simulation outputs are stored as structured artifacts tied to configurations, benchmarks, and hardware components, enabling systematic result exploration without custom parsers. We evaluate ArchSim on a 12 x 8 = 96-configuration simulation matrix spanning memory-bound, compute-bound, and mixed-intensity GPU workloads. Declarative simulation specifications drive full simulations with a median kernel time error of 0.18% relative to hand-written MGPUSim configurations across 95.8% of configurations. The platform introduces only 1.6 seconds of overhead per simulation, negligible relative to realistic simulation workloads.

cs.AR↗

arXiv2026

PeerMathDial: A Middle School Dialogue Dataset for Student Collaborative Math Problem Solving

Collaborative Problem Solving (CPS) is a core skill in education, where the process of peer interaction is highly important. However, existing educational dialogue datasets mostly focus on classroom instruction or tutoring (i.e., teacher/tutor-student interaction), yet datasets centering small-group, student-student interaction are limited. This thus leaves research with limited resources for studying how students interact, coordinate, and solve problems together in real educational settings. To address this, we introduce PeerMathDial, the first dataset of peer CPS dialogues collected from authentic middle school math classrooms. It contains 55 dialogues from 27 students, totaling 6,406 turns. To facilitate research on CPS discourse analysis, we further build a corpus-grounded dialogue act taxonomy assisted by LLMs. Using the dataset and the dialogue act taxonomy, we demonstrate the practical applications of PeerMathDial across three use cases. First, we track how dialogues evolve over time and measure the impact of teacher interventions. Second, we align dialogue actions with student surveys to reveal the connection between students' traits (e.g., confidence, leadership) and their actual behaviors. Third, by evaluating LLMs on dialogue act prediction, we glimpse at the potential of LLMs for student simulation in educational applications. Our dataset and source code will be released to the community.

cs.CL↗

arXiv2026

TheBotCompany: Self-Organizing Multi-agent Systems for Continuous Software Development

Large language model (LLM)-based multi-agent systems have shown promise in automating software development tasks. However, most vibe-coding systems focus on completing small tasks and incremental code changes, leaving persistent, continuous software development largely unexplored. We present TheBotCompany, an open-source orchestration framework for continuous multi-agent software development. TheBotCompany introduces three key innovations: (1) a three-phase state machine (Strategy to Execution to Verification) for milestone-driven development, (2) self-organizing agent teams where manager agents dynamically hire, assign, and retire worker agents based on project needs, and (3) asynchronous human oversight. We evaluate TheBotCompany on real-world software projects over multiple days of continuous development, measuring team adaptation patterns, milestone completion rates, cost efficiency, and code quality. Our results demonstrate that the self-organizing approach enables effective long-term software development with measurable progress, while the verification phase catches defects that would otherwise persist.

cs.SE↗

arXiv2026

Designing AI Peers for Collaborative Mathematical Problem Solving with Middle School Students: A Participatory Design Study

Collaborative problem solving (CPS) is a fundamental practice in middle-school mathematics education; however, student groups frequently stall or struggle without ongoing teacher support. Recent work has explored how Generative AI tools can be designed to support one-on-one tutoring, but little is known about how AI can be designed as peer learning partners in collaborative learning contexts. We conducted a participatory design study with 24 middle school students, who first engaged in mathematics CPS tasks with AI peers in a technology probe, and then collaboratively designed their ideal AI peer. Our findings reveal that students envision an AI peer as competent in mathematics yet explicitly deferential, providing progressive scaffolds such as hints and checks under clear student control. Students preferred a tone of friendly expertise over exaggerated personas. We also discuss design recommendations and implications for AI peers in middle school mathematics CPS.

cs.HC↗

arXiv2026

Real-Time Trend Prediction via Continually-Aligned LLM Query Generation

Trending news detection in low-traffic search environments faces a fundamental cold-start problem, where a lack of query volume prevents systems from identifying emerging or long-tail trends. Existing methods relying on keyword frequency or query spikes are inherently slow and ineffective in these sparse settings, lagging behind real-world shifts in attention. We introduce RTTP, a novel Real-Time Trending Prediction framework that generates search queries directly from news content instead of waiting for users to issue them. RTTP leverages a continual learning LLM (CL-LLM) that converts posts into search-style queries and scores them using engagement strength + creator authority, enabling early trend surfacing before search volume forms. To ensure adaptation without degrading reasoning, we propose Mix-Policy DPO, a new preference-based continual learning approach that combines on-policy stability with off-policy novelty to mitigate catastrophic forgetting during model upgrades. Deployed at production scale on Facebook and Meta AI products, RTTP delivers +91.4% improvement in tail-trend detection precision@500 and +19% query generation accuracy over industry baselines, while sustaining stable performance after multi-week online training. This work demonstrates that LLM-generated synthetic search signals, when aligned and continually updated, unlock timely trend understanding in low-traffic search environments.

cs.IR↗

arXiv2026

RecruitScope: A Visual Analytics System for Multidimensional Recruitment Data Analysis

Online recruitment platforms have become the dominant channel for modern hiring, yet most platforms offer only basic filtering capabilities, such as job title, keyword, and salary range. This hinders comprehensive analysis of multi-attribute relationships and job market patterns across different scales. We present RecruitScope, a visual analytics system designed to support multidimensional and cross-level exploration of recruitment data for job seekers and employers, particularly HR specialists. Through coordinated visualizations, RecruitScope enables users to analyze job positions and salary patterns from multiple perspectives, interpret industry dynamics at the macro level, and identify emerging positions at the micro level. We demonstrate the effectiveness of RecruitScope through case studies that reveal regional salary distribution patterns, characterize industry growth trajectories, and discover high-demand emerging roles in the job market.

cs.HC↗

arXiv2025

MathVC: An LLM-Simulated Multi-Character Virtual Classroom for Mathematics Education

Collaborative problem solving (CPS) is essential in mathematics education, fostering deeper learning through the exchange of ideas. Yet, classrooms often lack the resources, time, and peer dynamics needed to sustain productive CPS. Recent advancements in Large Language Models (LLMs) offer a promising avenue to enhance CPS in mathematical education. We designed and developed MathVC, a multi-persona LLM simulated virtual classroom platform to facilitate CPS in mathematics. MathVC combines a meta planning controller that monitors CPS stages-sense-making, team organization, planning, execution, validation, and predicts the next speaker, with a persona simulation stack that encodes mathematical thinking via a task schema and error-injected persona schemas seeded from teacher-specified misconceptions. We evaluated MathVC with 14 U.S. middle schoolers. Students reported constructive interaction and reaching shared solutions, describing gains in engagement, motivation, and confidence through diverse perspectives, immediate scaffolding, and human-like fallibility. Our findings also provide insights into simulating peers via LLM-based technologies for collaboration to support learning.

cs.CL↗

arXiv2025

DV365: Extremely Long User History Modeling at Instagram

Long user history is highly valuable signal for recommendation systems, but effectively incorporating it often comes with high cost in terms of data center power consumption and GPU. In this work, we chose offline embedding over end-to-end sequence length optimization methods to enable extremely long user sequence modeling as a cost-effective solution, and propose a new user embedding learning strategy, multi-slicing and summarization, that generates highly generalizable user representation of user's long-term stable interest. History length we encoded in this embedding is up to 70,000 and on average 40,000. This embedding, named as DV365, is proven highly incremental on top of advanced attentive user sequence models deployed in Instagram. Produced by a single upstream foundational model, it is launched in 15 different models across Instagram and Threads with significant impact, and has been production battle-proven for >1 year since our first launch.

cs.IR↗

arXiv2025

Will Your Next Pair Programming Partner Be Human? An Empirical Evaluation of Generative AI as a Collaborative Teammate in a Semester-Long Classroom Setting

Generative AI (GenAI), especially Large Language Models (LLMs), is rapidly reshaping both programming workflows and computer science education. Many programmers now incorporate GenAI tools into their workflows, including for collaborative coding tasks such as pair programming. While prior research has demonstrated the benefits of traditional pair programming and begun to explore GenAI-assisted coding, the role of LLM-based tools as collaborators in pair programming remains underexamined. In this work, we conducted a mixed-methods study with 39 undergraduate students to examine how GenAI influences collaboration, learning, and performance in pair programming. Specifically, students completed six in-class assignments under three conditions: Traditional Pair Programming (PP), Pair Programming with GenAI (PAI), and Solo Programming with GenAI (SAI). They used both LLM-based inline completion tools (e.g., GitHub Copilot) and LLM-based conversational tools (e.g., ChatGPT). Our results show that students in PAI achieved the highest assignment scores, whereas those in SAI attained the lowest. Additionally, students' attitudes toward LLMs' programming capabilities improved significantly after collaborating with LLM-based tools, and preferences were largely shaped by the perceived usefulness for completing assignments and learning programming skills, as well as the quality of collaboration. Our qualitative findings further reveal that while students appreciated LLM-based tools as valuable pair programming partners, they also identified limitations and had different expectations compared to human teammates. Our study provides one of the first empirical evaluations of GenAI as a pair programming collaborator through a comparison of three conditions (PP, PAI, and SAI). We also discuss the design implications and pedagogical considerations for future GenAI-assisted pair programming approaches.

cs.HC↗

arXiv2025

Understanding the Practices, Perceptions, and (Dis)Trust of Generative AI among Instructors: A Mixed-methods Study in the U.S. Higher Education

Generative AI (GenAI) has brought opportunities and challenges for higher education as it integrates into teaching and learning environments. As instructors navigate this new landscape, understanding their engagement with and attitudes toward GenAI is crucial. We surveyed 178 instructors from a single U.S. university to examine their current practices, perceptions, trust, and distrust of GenAI in higher education in March 2024. While most surveyed instructors reported moderate to high familiarity with GenAI-related concepts, their actual use of GenAI tools for direct instructional tasks remained limited. Our quantitative results show that trust and distrust in GenAI are related yet distinct; high trust does not necessarily imply low distrust, and vice versa. We also found significant differences in surveyed instructors' familiarity with GenAI across different trust and distrust groups. Our qualitative results show nuanced manifestations of trust and distrust among surveyed instructors and various approaches to support calibrated trust in GenAI. We discuss practical implications focused on (dis)trust calibration among instructors.

cs.HC↗

arXiv2024

TrustLLM: Trustworthiness in Large Language Models

Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and utility (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Finally, we emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. Knowing the specific trustworthy technologies that have been employed is crucial for analyzing their effectiveness.

cs.CL↗

arXiv2024

Evaluating the Effectiveness of LLMs in Introductory Computer Science Education: A Semester-Long Field Study

The integration of AI assistants, especially through the development of Large Language Models (LLMs), into computer science education has sparked significant debate. An emerging body of work has looked into using LLMs in education, but few have examined the impacts of LLMs on students in entry-level programming courses, particularly in real-world contexts and over extended periods. To address this research gap, we conducted a semester-long, between-subjects study with 50 students using CodeTutor, an LLM-powered assistant developed by our research team. Our study results show that students who used CodeTutor (the experimental group) achieved statistically significant improvements in their final scores compared to peers who did not use the tool (the control group). Within the experimental group, those without prior experience with LLM-powered tools demonstrated significantly greater performance gain than their counterparts. We also found that students expressed positive feedback regarding CodeTutor's capability, though they also had concerns about CodeTutor's limited role in developing critical thinking skills. Over the semester, students' agreement with CodeTutor's suggestions decreased, with a growing preference for support from traditional human teaching assistants. Our analysis further reveals that the quality of user prompts was significantly correlated with CodeTutor's response effectiveness. Building upon our results, we discuss the implications of our findings for integrating Generative AI literacy into curricula to foster critical thinking skills and turn to examining the temporal dynamics of user engagement with LLM-powered tools. We further discuss the discrepancy between the anticipated functions of tools and students' actual capabilities, which sheds light on the need for tailored strategies to improve educational outcomes.

cs.HC↗